AlphaCouncil
Unverified ML strategy on Multi by rahulmkarthik. BotFinder score 18 out of 100.
An autonomous risk-overlay system simulating a hedge fund Investment Committee. Uses Multi-Agent Architecture (LangGraph) to validate algorithmic signals by combining deep-learning
Source: github
BotFinder analysis pending.
AlphaCouncil
AlphaCouncil: Autonomous Investment Committee 🏛️ AlphaCouncil is an agentic risk-overlay system that orchestrates a "Man-vs-Machine" debate to validate algorithmic trading signals. Unlike traditional black-box quant models, AlphaCouncil uses a Multi-Agent Architecture (powered by LangGraph) to simulate a hedge fund Investment Committee. It combines deep-learning volatility forecasts with semantic reasoning to filter out false positives caused by event risk (earnings, macro news) or sector concentration. 🏗 Architecture AlphaCouncil operates as a Directed Acyclic Graph (DAG) with three specialized agents: 1. The Technician (Quant Agent): Role: Signal detection & Regime classification. Core Engine: VolSense (Custom PyTorch Volatility Forecaster). Logic: Analyzes Term Structure, Z-Scores, and Volatility Cones. 2. The Fundamentalist (Research Agent): Role: Event Risk & Sentiment analysis. Tools: Tavily Search API / RAG. Logic: Scans for earnings calls, lawsuits, and macro headwinds to reject "gambling" setups. 3. The Risk Manager (Risk and Execution Agent): Role: Portfolio construction &
⚠ No verified equity curve — no track-record source connected.
Drawdown profile
Data unavailable — contact the owner.
Verification ledger
How the score has moved
Recalculated at each data collection. Transparency means showing the bad weeks too.
No score history is stored yet — only the current score is shown.
Reviews & comments
No reviews collected from the source yet.
⚠ No live verification account connected — ask for proof before buying.
Alerts on changes: coming soon
Prop-firm compatibility not provided.
Open-source maintainer on GitHub.
Data-completeness & trust index (not a profitability rating)